[Misc] Warn about v0 in benchmark_paged_attn.py (#15495)

Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>

Author: tlrmchlsmth

benchmarks/kernels/benchmark_paged_attention.py

@@ -7,10 +7,13 @@
 import torch
 
 from vllm import _custom_ops as ops
+from vllm.logger import init_logger
 from vllm.platforms import current_platform
 from vllm.utils import (STR_DTYPE_TO_TORCH_DTYPE, FlexibleArgumentParser,
                         create_kv_caches_with_random)
 
+logger = init_logger(__name__)
+
 NUM_BLOCKS = 128 * 1024
 PARTITION_SIZE = 512
 PARTITION_SIZE_ROCM = 256
@@ -193,6 +196,9 @@ def run_cuda_benchmark(num_iters: int, profile: bool = False) -> float:
 
 
 if __name__ == '__main__':
+    logger.warning("This script benchmarks the paged attention kernel. "
+                   "By default this is no longer used in vLLM inference.")
+
     parser = FlexibleArgumentParser(
         description="Benchmark the paged attention kernel.")
     parser.add_argument("--version",